Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2111 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.3522. Min Act: -0.1700

Data Index: 65373 (Open Web Text)

Max Activating Token Index: 321

Text #1

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.3248. Min Act: -0.1700

Data Index: 8414524 (Open Web Text)

Max Activating Token Index: 763

Text #2

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.3026. Min Act: -0.1700

Data Index: 6498839 (Open Web Text)

Max Activating Token Index: 990

Text #3

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.2385. Min Act: -0.1700

Data Index: 5362557 (Open Web Text)

Max Activating Token Index: 302

Text #4

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.2671. Min Act: -0.1700

Data Index: 3848709 (Open Web Text)

Max Activating Token Index: 366

Text #5

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.2445. Min Act: -0.1700

Data Index: 7639806 (Open Web Text)

Max Activating Token Index: 734

Text #6

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.2181. Min Act: -0.1700

Data Index: 2984517 (Open Web Text)

Max Activating Token Index: 968

Text #7

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.1592. Min Act: -0.1700

Data Index: 6593473 (Open Web Text)

Max Activating Token Index: 44

Text #8

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.1610. Min Act: -0.1700

Data Index: 8759213 (Open Web Text)

Max Activating Token Index: 695

Text #9

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.1461. Min Act: -0.1700

Data Index: 3026912 (Open Web Text)

Max Activating Token Index: 262

Text #10

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.1533. Min Act: -0.1700

Data Index: 764375 (Open Web Text)

Max Activating Token Index: 239

Text #11

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.1169. Min Act: -0.1700

Data Index: 4102314 (Open Web Text)

Max Activating Token Index: 219

Text #12

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.1040. Min Act: -0.1700

Data Index: 2465204 (Open Web Text)

Max Activating Token Index: 839

Text #13

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.0908. Min Act: -0.1700

Data Index: 8173514 (Open Web Text)

Max Activating Token Index: 77

Text #14

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.0650. Min Act: -0.1700

Data Index: 7497371 (Open Web Text)

Max Activating Token Index: 1009

Text #15

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.0745. Min Act: -0.1700

Data Index: 2381189 (Open Web Text)

Max Activating Token Index: 578

Text #16

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.0463. Min Act: -0.1700

Data Index: 2787077 (Open Web Text)

Max Activating Token Index: 443

Text #17

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.0410. Min Act: -0.1700

Data Index: 7563952 (Open Web Text)

Max Activating Token Index: 522

Text #18

Max Range: 4.3522. Min Range: -4.3522

Max Act: 4.0476. Min Act: -0.1700

Data Index: 7784077 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 4.3522. Min Range: -4.3522

Max Act: 3.9972. Min Act: -0.1700

Data Index: 694478 (Open Web Text)

Max Activating Token Index: 961